CoolFace
Modelpublic

optimum-intel-internal-testing/tiny-random-CLIPModel

sourceHugging Faceupdated 11mo agoView on Hugging Face
0likes164kdownloads
tokenizer.json1843 linesDownload Raw Back to root
1{2  "version": "1.0",3  "truncation": null,4  "padding": null,5  "added_tokens": [6    {7      "id": 0,8      "content": "<|startoftext|>",9      "single_word": false,10      "lstrip": false,11      "rstrip": false,12      "normalized": true,13      "special": true14    },15    {16      "id": 1,17      "content": "<|endoftext|>",18      "single_word": false,19      "lstrip": false,20      "rstrip": false,21      "normalized": false,22      "special": true23    }24  ],25  "normalizer": {26    "type": "Sequence",27    "normalizers": [28      {29        "type": "NFC"30      },31      {32        "type": "Replace",33        "pattern": {34          "Regex": "\\s+"35        },36        "content": " "37      },38      {39        "type": "Lowercase"40      }41    ]42  },43  "pre_tokenizer": {44    "type": "Sequence",45    "pretokenizers": [46      {47        "type": "Split",48        "pattern": {49          "Regex": "<\\|startoftext\\|>|<\\|endoftext\\|>|'s|'t|'re|'ve|'m|'ll|'d|[\\p{L}]+|[\\p{N}]|[^\\s\\p{L}\\p{N}]+"50        },51        "behavior": "Removed",52        "invert": true53      },54      {55        "type": "ByteLevel",56        "add_prefix_space": false,57        "trim_offsets": true,58        "use_regex": true59      }60    ]61  },62  "post_processor": {63    "type": "RobertaProcessing",64    "sep": [65      "<|endoftext|>",66      167    ],68    "cls": [69      "<|startoftext|>",70      071    ],72    "trim_offsets": false,73    "add_prefix_space": false74  },75  "decoder": {76    "type": "ByteLevel",77    "add_prefix_space": true,78    "trim_offsets": true,79    "use_regex": true80  },81  "model": {82    "type": "BPE",83    "dropout": null,84    "unk_token": "<|endoftext|>",85    "continuing_subword_prefix": "",86    "end_of_word_suffix": "</w>",87    "fuse_unk": false,88    "vocab": {89      "<|startoftext|>": 0,90      "<|endoftext|>": 1,91      "!": 2,92      "\"": 3,93      "#": 4,94      "$": 5,95      "%": 6,96      "&": 7,97      "'": 8,98      "(": 9,99      ")": 10,100      "*": 11,101      "+": 12,102      ",": 13,103      "-": 14,104      ".": 15,105      "/": 16,106      "0": 17,107      "1": 18,108      "2": 19,109      "3": 20,110      "4": 21,111      "5": 22,112      "6": 23,113      "7": 24,114      "8": 25,115      "9": 26,116      ":": 27,117      ";": 28,118      "<": 29,119      "=": 30,120      ">": 31,121      "?": 32,122      "@": 33,123      "[": 34,124      "\\": 35,125      "]": 36,126      "^": 37,127      "_": 38,128      "`": 39,129      "a": 40,130      "b": 41,131      "c": 42,132      "d": 43,133      "e": 44,134      "f": 45,135      "g": 46,136      "h": 47,137      "i": 48,138      "j": 49,139      "k": 50,140      "l": 51,141      "m": 52,142      "n": 53,143      "o": 54,144      "p": 55,145      "q": 56,146      "r": 57,147      "s": 58,148      "t": 59,149      "u": 60,150      "v": 61,151      "w": 62,152      "x": 63,153      "y": 64,154      "z": 65,155      "|": 66,156      "}": 67,157      "~": 68,158      "¡": 69,159      "¢": 70,160      "£": 71,161      "¤": 72,162      "¥": 73,163      "¦": 74,164      "§": 75,165      "¨": 76,166      "©": 77,167      "ª": 78,168      "«": 79,169      "¬": 80,170      "®": 81,171      "¯": 82,172      "°": 83,173      "±": 84,174      "²": 85,175      "³": 86,176      "´": 87,177      "µ": 88,178      "¶": 89,179      "·": 90,180      "¸": 91,181      "¹": 92,182      "º": 93,183      "»": 94,184      "¼": 95,185      "½": 96,186      "¾": 97,187      "¿": 98,188      "Â": 99,189      "Ã": 100,190      "Ä": 101,191      "Å": 102,192      "Æ": 103,193      "Ç": 104,194      "È": 105,195      "É": 106,196      "Ê": 107,197      "Ë": 108,198      "Ì": 109,199      "Í": 110,200      "Î": 111,201      "Ï": 112,202      "Ð": 113,203      "Ñ": 114,204      "Ö": 115,205      "×": 116,206      "Ø": 117,207      "Ù": 118,208      "Ü": 119,209      "à": 120,210      "á": 121,211      "â": 122,212      "ã": 123,213      "ä": 124,214      "å": 125,215      "æ": 126,216      "ç": 127,217      "è": 128,218      "é": 129,219      "ë": 130,220      "ì": 131,221      "ï": 132,222      "Ģ": 133,223      "ģ": 134,224      "Ĥ": 135,225      "ĥ": 136,226      "Ħ": 137,227      "ħ": 138,228      "Ĩ": 139,229      "ĩ": 140,230      "Ī": 141,231      "ī": 142,232      "Ĭ": 143,233      "ĭ": 144,234      "Į": 145,235      "į": 146,236      "İ": 147,237      "ı": 148,238      "IJ": 149,239      "ij": 150,240      "Ĵ": 151,241      "ĵ": 152,242      "Ķ": 153,243      "ķ": 154,244      "ĸ": 155,245      "Ĺ": 156,246      "ĺ": 157,247      "Ļ": 158,248      "ļ": 159,249      "Ľ": 160,250      "ľ": 161,251      "Ŀ": 162,252      "ŀ": 163,253      "Ł": 164,254      "ł": 165,255      "Ń": 166,256      "s</w>": 167,257      "m</w>": 168,258      "t</w>": 169,259      "i</w>": 170,260      "p</w>": 171,261      "y</w>": 172,262      "n</w>": 173,263      "r</w>": 174,264      "a</w>": 175,265      "e</w>": 176,266      "w</w>": 177,267      "g</w>": 178,268      "l</w>": 179,269      "o</w>": 180,270      "d</w>": 181,271      "c</w>": 182,272      "h</w>": 183,273      "z</w>": 184,274      "k</w>": 185,275      "¡</w>": 186,276      "u</w>": 187,277      "ĺ</w>": 188,278      "ĥ</w>": 189,279      "IJ</w>": 190,280      "º</w>": 191,281      "f</w>": 192,282      "j</w>": 193,283      "b</w>": 194,284      "ª</w>": 195,285      "v</w>": 196,286      "Ķ</w>": 197,287      "£</w>": 198,288      "ĩ</w>": 199,289      "¿</w>": 200,290      "Ń</w>": 201,291      "©</w>": 202,292      "ŀ</w>": 203,293      "³</w>": 204,294      "x</w>": 205,295      "Ĭ</w>": 206,296      "¦</w>": 207,297      "Ĥ</w>": 208,298      "ĭ</w>": 209,299      "«</w>": 210,300      "¹</w>": 211,301      "Ł</w>": 212,302      "Ĵ</w>": 213,303      "ĸ</w>": 214,304      "Ĺ</w>": 215,305      "¼</w>": 216,306      "į</w>": 217,307      "±</w>": 218,308      "Ģ</w>": 219,309      "ī</w>": 220,310      "®</w>": 221,311      "¬</w>": 222,312      "²</w>": 223,313      "·</w>": 224,314      "ł</w>": 225,315      "Ļ</w>": 226,316      "Ħ</w>": 227,317      "'</w>": 228,318      "ĵ</w>": 229,319      "¢</w>": 230,320      "¨</w>": 231,321      "°</w>": 232,322      "&</w>": 233,323      ":</w>": 234,324      "(</w>": 235,325      "¤</w>": 236,326      "¾</w>": 237,327      "Ĩ</w>": 238,328      "ı</w>": 239,329      "¸</w>": 240,330      "µ</w>": 241,331      ",</w>": 242,332      "q</w>": 243,333      "ij</w>": 244,334      "»</w>": 245,335      "ģ</w>": 246,336      "Į</w>": 247,337      "¯</w>": 248,338      "¶</w>": 249,339      "^</w>": 250,340      "1</w>": 251,341      "ľ</w>": 252,342      "4</w>": 253,343      "0</w>": 254,344      "Ŀ</w>": 255,345      "½</w>": 256,346      "[</w>": 257,347      "5</w>": 258,348      ".</w>": 259,349      "§</w>": 260,350      "´</w>": 261,351      "-</w>": 262,352      "ķ</w>": 263,353      "¥</w>": 264,354      "~</w>": 265,355      "Ī</w>": 266,356      "|</w>": 267,357      "!</w>": 268,358      ";</w>": 269,359      "Ľ</w>": 270,360      ")</w>": 271,361      "ħ</w>": 272,362      "/</w>": 273,363      "7</w>": 274,364      "3</w>": 275,365      "`</w>": 276,366      "*</w>": 277,367      "#</w>": 278,368      "ļ</w>": 279,369      "$</w>": 280,370      "@</w>": 281,371      "_</w>": 282,372      "=</w>": 283,373      "]</w>": 284,374      "<</w>": 285,375      "\"</w>": 286,376      "\\</w>": 287,377      "8</w>": 288,378      "9</w>": 289,379      "%</w>": 290,380      "></w>": 291,381      "?</w>": 292,382      "2</w>": 293,383      "İ</w>": 294,384      "+</w>": 295,385      "}</w>": 296,386      "6</w>": 297,387      "th": 298,388      "the</w>": 299,389      "in": 300,390      "an": 301,391      "ed</w>": 302,392      "er": 303,393      "re": 304,394      "ar": 305,395      "ti": 306,396      "on": 307,397      "en": 308,398      "of</w>": 309,399      "or": 310,400      "and</w>": 311,401      "er</w>": 312,402      "on</w>": 313,403      "in</w>": 314,404      "ing</w>": 315,405      "st": 316,406      "ro": 317,407      "al": 318,408      "it": 319,409      "to</w>": 320,410      "as</w>": 321,411      "at": 322,412      "es</w>": 323,413      "ou": 324,414      "hi": 325,415      "ac": 326,416      "si": 327,417      "at</w>": 328,418      "ri": 329,419      "al</w>": 330,420      "el": 331,421      "an</w>": 332,422      "am": 333,423      "or</w>": 334,424      "st</w>": 335,425      "li": 336,426      "ur": 337,427      "ec": 338,428      "om": 339,429      "di": 340,430      "was</w>": 341,431      "ly</w>": 342,432      "en</w>": 343,433      "ea": 344,434      "ch": 345,435      "un": 346,436      "tion</w>": 347,437      "la": 348,438      "is</w>": 349,439      "fi": 350,440      "ol": 351,441      "de": 352,442      "-@</w>": 353,443      "@-@</w>": 354,444      "ra": 355,445      "vi": 356,446      "le</w>": 357,447      "lo": 358,448      "sh": 359,449      "em": 360,450      "be": 361,451      "that</w>": 362,452      "'s</w>": 363,453      "con": 364,454      "ma": 365,455      "for</w>": 366,456      "ha": 367,457      "su": 368,458      "by</w>": 369,459      "ith</w>": 370,460      "ve</w>": 371,461      "with</w>": 372,462      "se</w>": 373,463      "ch</w>": 374,464      "the": 375,465      "ent": 376,466      "po": 377,467      "ce</w>": 378,468      "il": 379,469      "se": 380,470      "ent</w>": 381,471      "le": 382,472      "com": 383,473      "sp": 384,474      "ere</w>": 385,475      "pro": 386,476      "no": 387,477      "bu": 388,478      "wh": 389,479      "it</w>": 390,480      "th</w>": 391,481      "ver": 392,482      "ne": 393,483      "ca": 394,484      "is": 395,485      "for": 396,486      "ag": 397,487      "ers</w>": 398,488      "mo": 399,489      "gh": 400,490      "fro": 401,491      "ted</w>": 402,492      "from</w>": 403,493      "tion": 404,494      "op": 405,495      "his</w>": 406,496      "ad": 407,497      "ab": 408,498      "ic": 409,499      "he</w>": 410,500      "oun": 411,501      "as": 412,502      "ts</w>": 413,503      "sc": 414,504      "de</w>": 415,505      "ow": 416,506      "ex": 417,507      "whi": 418,508      "ru": 419,509      "ter</w>": 420,510      "ap": 421,511      "ds</w>": 422,512      "were</w>": 423,513      "pre": 424,514      "du": 425,515      "gu": 426,516      "par": 427,517      "ir": 428,518      "bo": 429,519      "ther</w>": 430,520      "qu": 431,521      "lu": 432,522      "ter": 433,523      "tw": 434,524      "es": 435,525      "rec": 436,526      "per": 437,527      "ta": 438,528      "ate</w>": 439,529      "ver</w>": 440,530      "ated</w>": 441,531      "ding</w>": 442,532      "ity</w>": 443,533      "man": 444,534      "ear": 445,535      "sed</w>": 446,536      "ded</w>": 447,537      "au": 448,538      "all</w>": 449,539      "ame</w>": 450,540      "ci": 451,541      "one</w>": 452,542      "ing": 453,543      "are</w>": 454,544      "af": 455,545      "ir</w>": 456,546      "ation</w>": 457,547      "âĢ": 458,548      "had</w>": 459,549      "tr": 460,550      "ul": 461,551      "ld</w>": 462,552      "which</w>": 463,553      "wa": 464,554      "im": 465,555      "lea": 466,556      "be</w>": 467,557      "to": 468,558      "tim": 469,559      "fir": 470,560      "wor": 471,561      "ong</w>": 472,562      "por": 473,563      "mar": 474,564      "me": 475,565      "ally</w>": 476,566      "so</w>": 477,567      "out</w>": 478,568      "tions</w>": 479,569      "its</w>": 480,570      "gh</w>": 481,571      "ge</w>": 482,572      "ber</w>": 483,573      "fe": 484,574      "pu": 485,575      "ser": 486,576      "der": 487,577      "pl": 488,578      "ss</w>": 489,579      "ine</w>": 490,580      "inc": 491,581      "mi": 492,582      "ght</w>": 493,583      "go": 494,584      "this</w>": 495,585      "tur": 496,586      "da": 497,587      "rou": 498,588      "but</w>": 499,589      "um": 500,590      "son</w>": 501,591      "we": 502,592      "ved</w>": 503,593      "sion</w>": 504,594      "ke</w>": 505,595      "pla": 506,596      "their</w>": 507,597      "ies</w>": 508,598      "first</w>": 509,599      "sa": 510,600      "oc": 511,601      "att": 512,602      "of": 513,603      "pe": 514,604      "not</w>": 515,605      "gi": 516,606      "na": 517,607      "ary</w>": 518,608      "mu": 519,609      "led</w>": 520,610      "âĢĵ</w>": 521,611      "her</w>": 522,612      "ran": 523,613      "co": 524,614      "they</w>": 525,615      "der</w>": 526,616      "ali": 527,617      "also</w>": 528,618      "ore</w>": 529,619      "ep": 530,620      "ould</w>": 531,621      "after</w>": 532,622      "shi": 533,623      "us</w>": 534,624      "et</w>": 535,625      "tic": 536,626      "stor": 537,627      "wi": 538,628      "ev": 539,629      "other</w>": 540,630      "sh</w>": 541,631      "ting</w>": 542,632      "ard</w>": 543,633      "te": 544,634      "two</w>": 545,635      "ni": 546,636      "have</w>": 547,637      "our": 548,638      "comm": 549,639      "te</w>": 550,640      "ack</w>": 551,641      "oo": 552,642      "fin": 553,643      "sec": 554,644      "ents</w>": 555,645      "has</w>": 556,646      "comp": 557,647      "bec": 558,648      "ks</w>": 559,649      "cont": 560,650      "land</w>": 561,651      "been</w>": 562,652      "ence</w>": 563,653      "king</w>": 564,654      "el</w>": 565,655      "age</w>": 566,656      "low": 567,657      "min": 568,658      ".@</w>": 569,659      "@.@</w>": 570,660      "ome</w>": 571,661      "ment</w>": 572,662      "char": 573,663      "ge": 574,664      "ater</w>": 575,665      "nor": 576,666      "ho": 577,667      "ous</w>": 578,668      "who</w>": 579,669      "ear</w>": 580,670      "spec": 581,671      "col": 582,672      "ely</w>": 583,673      "ty</w>": 584,674      "jo": 585,675      "uring</w>": 586,676      "duc": 587,677      "bri": 588,678      "str": 589,679      "can": 590,680      "ori": 591,681      "tra": 592,682      "pa": 593,683      "she</w>": 594,684      "do": 595,685      "tive</w>": 596,686      "mon": 597,687      "new</w>": 598,688      "rit": 599,689      "time</w>": 600,690      "ons</w>": 601,691      "so": 602,692      "man</w>": 603,693      "dec": 604,694      "cent": 605,695      "lan": 606,696      "pi": 607,697      "our</w>": 608,698      "inter": 609,699      "fer": 610,700      "gra": 611,701      "gre": 612,702      "res</w>": 613,703      "inclu": 614,704      "mil": 615,705      "during</w>": 616,706      "own</w>": 617,707      "pres": 618,708      "ju": 619,709      "ned</w>": 620,710      "ell</w>": 621,711      ",@</w>": 622,712      "@,@</w>": 623,713      "ite</w>": 624,714      "gen": 625,715      "when</w>": 626,716      "sig": 627,717      "bi": 628,718      "ren": 629,719      "fa": 630,720      "ga": 631,721      "play": 632,722      "eng": 633,723      "tional</w>": 634,724      "ound</w>": 635,725      "thou": 636,726      "more</w>": 637,727      "ree</w>": 638,728      "ember</w>": 639,729      "ei": 640,730      "sou": 641,731      "sur": 642,732      "sti": 643,733      "car": 644,734      "form": 645,735      "lar": 646,736      "ses</w>": 647,737      "ten": 648,738      "into</w>": 649,739      "tu": 650,740      "ces</w>": 651,741      "most</w>": 652,742      "ked</w>": 653,743      "way</w>": 654,744      "cre": 655,745      "coun": 656,746      "up</w>": 657,747      "les</w>": 658,748      "ace</w>": 659,749      "als</w>": 660,750      "ke": 661,751      "would</w>": 662,752      "ant</w>": 663,753      "ber": 664,754      "fu": 665,755      "ited</w>": 666,756      "pri": 667,757      "while</w>": 668,758      "over</w>": 669,759      "ings</w>": 670,760      "re</w>": 671,761      "fil": 672,762      "sy": 673,763      "est": 674,764      "able</w>": 675,765      "wn</w>": 676,766      "sea": 677,767      "ach": 678,768      "sing</w>": 679,769      "ins</w>": 680,770      "tic</w>": 681,771      "id</w>": 682,772      "only</w>": 683,773      "ates</w>": 684,774      "tri": 685,775      "ving</w>": 686,776      "ba": 687,777      "vel": 688,778      "ance</w>": 689,779      "sta": 690,780      "ern</w>": 691,781      "fol": 692,782      "een</w>": 693,783      "ined</w>": 694,784      "stru": 695,785      "uni": 696,786      "game</w>": 697,787      "lar</w>": 698,788      "sel": 699,789      "bli": 700,790      "used</w>": 701,791      "ning</w>": 702,792      "ps</w>": 703,793      "ties</w>": 704,794      "kno": 705,795      "cor": 706,796      "ft</w>": 707,797      "recor": 708,798      "ble</w>": 709,799      "vie": 710,800      "ys</w>": 711,801      "wil": 712,802      "ical</w>": 713,803      "app": 714,804      "tro": 715,805      "three</w>": 716,806      "cla": 717,807      "old</w>": 718,808      "shed</w>": 719,809      "hea": 720,810      "about</w>": 721,811      "writ": 722,812      "than</w>": 723,813      "ste": 724,814      "later</w>": 725,815      "ari": 726,816      "dy</w>": 727,817      "publi": 728,818      "loc": 729,819      "aga": 730,820      "throu": 731,821      "ssi": 732,822      "end</w>": 733,823      "may</w>": 734,824      "ang": 735,825      "ach</w>": 736,826      "ves</w>": 737,827      "og": 738,828      "him</w>": 739,829      "betw": 740,830      "though</w>": 741,831      "between</w>": 742,832      "um</w>": 743,833      "star": 744,834      "scri": 745,835      "rea": 746,836      "ond</w>": 747,837      "ship</w>": 748,838      "ok</w>": 749,839      "hel": 750,840      "song</w>": 751,841      "chi": 752,842      "cap": 753,843      "ever</w>": 754,844      "day</w>": 755,845      "cri": 756,846      "some</w>": 757,847      "bro": 758,848      "no</w>": 759,849      "there</w>": 760,850      "ans</w>": 761,851      "all": 762,852      "num": 763,853      "red</w>": 764,854      "ears</w>": 765,855      "sts</w>": 766,856      "any</w>": 767,857      "war": 768,858      "ph": 769,859      "pp": 770,860      "gin": 771,861      "struc": 772,862      "amer": 773,863      "produc": 774,864      "sch": 775,865      "ces": 776,866      "ure</w>": 777,867      "ating</w>": 778,868      "emp": 779,869      "tor": 780,870      "season</w>": 781,871      "fore</w>": 782,872      "ic</w>": 783,873      "city</w>": 784,874      "gro": 785,875      "follow": 786,876      "sub": 787,877      "bel": 788,878      "year</w>": 789,879      "can</w>": 790,880      "sin": 791,881      "where</w>": 792,882      "and": 793,883      "made</w>": 794,884      "relea": 795,885      "sm": 796,886      "bl": 797,887      "ten</w>": 798,888      "with": 799,889      "son": 800,890      "many</w>": 801,891      "are": 802,892      "ed": 803,893      "how": 804,894      "americ": 805,895      "ury</w>": 806,896      "stu": 807,897      "musi": 808,898      "cu": 809,899      "nam": 810,900      "ement</w>": 811,901      "such</w>": 812,902      "albu": 813,903      "buil": 814,904      "before</w>": 815,905      "ef": 816,906      "arm": 817,907      "ton</w>": 818,908      "them</w>": 819,909      "cal": 820,910      "bar": 821,911      "des</w>": 822,912      "mat": 823,913      "gener": 824,914      "od</w>": 825,915      "series</w>": 826,916      "cer": 827,917      "sho": 828,918      "enti": 829,919      "her": 830,920      "over": 831,921      "ann": 832,922      "well</w>": 833,923      "world</w>": 834,924      "gan</w>": 835,925      "est</w>": 836,926      "second</w>": 837,927      "ters</w>": 838,928      "side</w>": 839,929      "tran": 840,930      "line</w>": 841,931      "ture</w>": 842,932      "port</w>": 843,933      "being</w>": 844,934      "years</w>": 845,935      "both</w>": 846,936      "indi": 847,937      "these</w>": 848,938      "national</w>": 849,939      "histor": 850,940      "fe</w>": 851,941      "vo": 852,942      "sted</w>": 853,943      "ani": 854,944      "bas": 855,945      "poin": 856,946      "sing": 857,947      "film</w>": 858,948      "pen": 859,949      "sup": 860,950      "mis": 861,951      "cro": 862,952      "stri": 863,953      "lin": 864,954      "tre": 865,955      "war</w>": 866,956      "however</w>": 867,957      "ying</w>": 868,958      "ling</w>": 869,959      "yp": 870,960      "ected</w>": 871,961      "direc": 872,962      "vision</w>": 873,963      "album</w>": 874,964      "then</w>": 875,965      "ll</w>": 876,966      "sever": 877,967      "through</w>": 878,968      "known</w>": 879,969      "bor": 880,970      "cul": 881,971      "clu": 882,972      "ster</w>": 883,973      "south</w>": 884,974      "ry</w>": 885,975      "ect</w>": 886,976      "low</w>": 887,977      "pr": 888,978      "sk": 889,979      "iso": 890,980      "north</w>": 891,981      "part</w>": 892,982      "fac": 893,983      "tly</w>": 894,984      "peri": 895,985      "eu": 896,986      "batt": 897,987      "state</w>": 898,988      "ced</w>": 899,989      "consi": 900,990      "inf": 901,991      "poli": 902,992      "olog": 903,993      "early</w>": 904,994      "posi": 905,995      "ames</w>": 906,996      "win": 907,997      "devel": 908,998      "ob": 909,999      "ve": 910,1000      "ven</w>": 911,1001      "oper": 912,1002      "ger": 913,1003      "offi": 914,1004      "charac": 915,1005      "ms</w>": 916,1006      "high": 917,1007      "ad</w>": 918,1008      "tho": 919,1009      "several</w>": 920,1010      "dre": 921,1011      "descri": 922,1012      "ale</w>": 923,1013      "number</w>": 924,1014      "air": 925,1015      "including</w>": 926,1016      "inst</w>": 927,1017      "against</w>": 928,1018      "ls</w>": 929,1019      "sul": 930,1020      "episo": 931,1021      "cam": 932,1022      "dif": 933,1023      "soci": 934,1024      "became</w>": 935,1025      "like</w>": 936,1026      "tel": 937,1027      "four</w>": 938,1028      "âĢĶ</w>": 939,1029      "hou": 940,1030      "joh": 941,1031      "united</w>": 942,1032      "inv": 943,1033      "under</w>": 944,1034      "nov": 945,1035      "tiv": 946,1036      "suc": 947,1037      "ations</w>": 948,1038      "ack": 949,1039      "tor</w>": 950,1040      "ron": 951,1041      "und</w>": 952,1042      "ws</w>": 953,1043      "fo": 954,1044      "gr": 955,1045      "develop": 956,1046      "although</w>": 957,1047      "contin": 958,1048      "west</w>": 959,1049      "origin": 960,1050      "music</w>": 961,1051      "ors</w>": 962,1052      "don</w>": 963,1053      "century</w>": 964,1054      "ward</w>": 965,1055      "work</w>": 966,1056      "me</w>": 967,1057      "ami": 968,1058      "cha": 969,1059      "very</w>": 970,1060      "har": 971,1061      "dis": 972,1062      "zed</w>": 973,1063      "do</w>": 974,1064      "gs</w>": 975,1065      "tow": 976,1066      "sol": 977,1067      "following</w>": 978,1068      "lion</w>": 979,1069      "rema": 980,1070      "ns</w>": 981,1071      "tish</w>": 982,1072      "chur": 983,1073      "som": 984,1074      "mp": 985,1075      "tle</w>": 986,1076      "gover": 987,1077      "del": 988,1078      "comple": 989,1079      "cur": 990,1080      "use</w>": 991,1081      "back</w>": 992,1082      "hu": 993,1083      "stern</w>": 994,1084      "began</w>": 995,1085      "fiel": 996,1086      "ause</w>": 997,1087      "dra": 998,1088      "pas": 999,1089      "bil": 1000,1090      "cation</w>": 1001,1091      "dent</w>": 1002,1092      "bed</w>": 1003,1093      "because</w>": 1004,1094      "ant": 1005,1095      "eam</w>": 1006,1096      "phi": 1007,1097      "yo": 1008,1098      "continu": 1009,1099      "tain</w>": 1010,1100      "try</w>": 1011,1101      "fre": 1012,1102      "peop": 1013,1103      "called</w>": 1014,1104      "found</w>": 1015,1105      "episode</w>": 1016,1106      "desig": 1017,1107      "mor": 1018,1108      "set</w>": 1019,1109      "ley</w>": 1020,1110      "east</w>": 1021,1111      "trac": 1022,1112      "cra": 10231113    },1114    "merges": [1115      "t h",1116      "th e</w>",1117      "i n",1118      "a n",1119      "e d</w>",1120      "e r",1121      "r e",1122      "a r",1123      "t i",1124      "o n",1125      "e n",1126      "o f</w>",1127      "o r",1128      "an d</w>",1129      "e r</w>",1130      "o n</w>",1131      "i n</w>",1132      "in g</w>",1133      "s t",1134      "r o",1135      "a l",1136      "i t",1137      "t o</w>",1138      "a s</w>",1139      "a t",1140      "e s</w>",1141      "o u",1142      "h i",1143      "a c",1144      "s i",1145      "a t</w>",1146      "r i",1147      "a l</w>",1148      "e l",1149      "a n</w>",1150      "a m",1151      "o r</w>",1152      "s t</w>",1153      "l i",1154      "u r",1155      "e c",1156      "o m",1157      "d i",1158      "w as</w>",1159      "l y</w>",1160      "e n</w>",1161      "e a",1162      "c h",1163      "u n",1164      "ti on</w>",1165      "l a",1166      "i s</w>",1167      "f i",1168      "o l",1169      "d e",1170      "- @</w>",1171      "@ -@</w>",1172      "r a",1173      "v i",1174      "l e</w>",1175      "l o",1176      "s h",1177      "e m",1178      "b e",1179      "th at</w>",1180      "' s</w>",1181      "c on",1182      "m a",1183      "f or</w>",1184      "h a",1185      "s u",1186      "b y</w>",1187      "it h</w>",1188      "v e</w>",1189      "w ith</w>",1190      "s e</w>",1191      "c h</w>",1192      "th e",1193      "en t",1194      "p o",1195      "c e</w>",1196      "i l",1197      "s e",1198      "en t</w>",1199      "l e",1200      "c om",

Showing the first 1,200 of 1843 lines. Download the file for the rest.